There has been substantial work in recent years on grounded language acquisition, in which a model is learned that relates linguistic constructs to the perceivable world. While powerful, this approach is frequently hindered by ambiguities and omissions found in natural language. One such omission is the lack of negative labels on objects. We describe an unsupervised system that learns visual classifiers associated with words, using semantic similarity to automatically choose negative examples from a corpus of perceptual and linguistic data. We evaluate the effectiveness of each stage as well as the system's performance on the overall learning task.
展开▼